Design and validation of an artificial intelligence embedded system for the detection of Cerambyx cerdo Linnaeus 1758 in common oaks and holm oaks.

This research focuses on the use of Artificial Intelligence embedded for real-time detection of Cerambyx cerdo larvae in holm oaks and common oaks. The work has been carried out in the framework of the Horizon Europe project DRYAD. To do this, 2 live Cerambyx larvae were captured, the sound of these insects was recorded in the laboratory and, based on the files obtained, an Artificial Intelligence algorithm was created for the detection of Cerambyx cerdo. Subsequently, the algorithm has been adapted to be used in the 32-bit microcontroller of the Termidetect ® brand IoT device. The algorithm was validated in a group of 10 trees located on a Mediterranean Agrosilvopastoral Ecosystem (MAE) parcel in the province of Salamanca. This study demonstrates the feasibility of using IoT devices with Artificial Intelligence embedded for detection of Cerambyx larvae in holm oaks and common oaks.